--- schema_version: "1" id: ccb65c8f657987a5454a0a60d816f2f1da67d6a910bb5777c7355b5097cc053d title: Agentforce Voice collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/agentforce_voice.md canonical_url: https://help.salesforce.com/s/articleView?id=ai.agentforce_voice.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: abdb3c34b4c8ded1f8f704ec1dff6ab08d26fe0a9e20027db8fa192dee374231 description: Agentforce Voice enables Agentforce Service agents to speak and understand voice conversations with customers. It is designed to understand customer intent from spoken input and take actions to resolve customer queries. products: - Agentforce - Cross Cloud release: "264" --- # Agentforce Voice Agentforce Voice enables Agentforce Service agents to speak and understand voice conversations with customers. It is designed to understand customer intent from spoken input and take actions to resolve customer queries. ### Required Editions
Available in: Lightning Experience
Available in: Enterprise, Unlimited, and Developer Editions with Foundations or Agentforce 1 Editions, and Salesforce Voice add-ons.
![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png) Note Agentforce Voice is supported only in English. Agentforce Voice uses multiple models to handle voice interactions. - The user’s spoken words are first converted to text using a speech-to-text model, such as Deepgram. - The transcribed text is then processed by a Flash Planner, which functions like the Salesforce Atlas reasoning engine. Using an OpenAI GPT large language model (LLM), the most relevant subagent and actions are identified to use to respond to the user’s query, resulting in a text response. - Finally, the generated text is converted back to audio using a text-to-speech model and delivered to the user using a text-to-speech model, such as ElevenLabs. We have built-in instructions and guardrails to help make sure agent responses are clear, easily understood, and follow content safety and security policies. These instructions are integrated into the Flash Planner to manage interactions. These are a few examples of what the built-in instructions and guardrails accomplish. - Optimize spoken delivery: Instructions on how agents format spoken replies, such as strategic pauses for clarity when conveying information like addresses. For example, separating numbers from street names. - Provide concise responses: Guiding agents by word limits to prevent lengthy responses. - Help ensure content safety: Guardrails to help prevent toxic or offensive language in agent responses and safeguard proprietary information. ## Zero Data Retention Policies Your data isn’t retained by third-party LLMs. We partner with all our external model providers, such as OpenAI, to enforce the zero-data retention policy. - Large Language Models: We partner with all our external large language model (LLM) providers to enforce the zero-data retention policy. For more details on other trust related issues, see [Trust and Agentforce](https://help.salesforce.com/s/articleView?id=ai.copilot_trust.htm&release=264.0.0&type=5). - Deepgram: We use a dedicated opt-out mechanism that Deepgram provides to make sure data is only retained for the duration necessary to process the request and not utilized for model improvement. - ElevenLabs: We use ElevenLabs zero retention mode, an enhanced privacy feature to make sure the data from our requests and responses is immediately deleted upon completing the request. The specialized mode restricts the logging of sensitive data points, ensuring they are never sent to a database for long-term storage. ElevenLabs also has agreements with third-party LLM providers that prevent them from training their models on customer data. ## Agentforce Voice Use Cases Autonomously address customer inquiries with natural speech by deploying voice-enabled service agents to telephony channels. By leveraging Agentforce Voice, these agents replace traditional, static IVR hierarchies with dynamic, intent-driven conversations. See [Choose Your Telephony Provider for Voice-Enabled Agents](https://help.salesforce.com/s/articleView?id=ai.agentforce_voice_telephony_overview.htm&release=264.0.0&type=5 "Route voice conversations to your voice-enabled Agentforce Service agents. Voice-enabled agents use Agentforce Voice features to provide the autonomous AI layer for your contact center. Agentforce Voice replaces static, hierarchical IVR logic with dynamic, intent-driven conversations."). Offer customers a more engaging and accessible way to interact with your service agents. With Agentforce Voice for Enhanced Chat v2, customers can seamlessly switch between text and voice mode. A transcript appears in the chat window as your customer and the agent speak, so users can switch between talking and messaging without losing the thread. Easily set up a voice-enabled service agent and connect it to a Enhanced Chat v2 deployment in Agentforce Builder. See [Connect a Service Agent to Enhanced Chat v2](https://help.salesforce.com/s/articleView?id=ai.service_agent_deploy_enhanced_chat_v2.htm&release=264.0.0&type=5 "To connect an agent to Enhanced Chat v2 in the new Agentforce Builder, set up the Enhanced Chat v2 connection. Agentforce Builder creates the channel and Enhanced Chat v2 deployment for you. Set up Agentforce Voice for Enhanced Chat v2 so that users can switch between speech and text when they chat with an Agentforce Service agent."). #### See Also - [Connect a Service Agent to Partner Telephony](https://help.salesforce.com/s/articleView?id=ai.agent_connect_telephony_parent.htm&release=264.0.0&type=5 "Route voice conversations to your Agentforce Service agents. Learn how to create a telephony connection to your partner telephony system, configure voice mode settings, and route calls to your agent.") - [_Video_: Set Up a Voice-Enabled Agent in Agentforce](https://salesforce.vidyard.com/watch/7UjuTize5zUoSPooDJyN2V)